Alpha55 / R1 /experiment_config.json

The final model (R1) is now out.

b776003 verified 3 months ago

199 Bytes

{
    "model_type": "encoder-decoder-transformer",
    "d_model": 256,
    "layers": {
        "encoder": 3,
        "decoder": 3
    },
    "vocab_size": 32000,
    "parameters": 30137600
}

	{
	"model_type": "encoder-decoder-transformer",
	"d_model": 256,
	"layers": {
	"encoder": 3,
	"decoder": 3
	},
	"vocab_size": 32000,
	"parameters": 30137600
	}